© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14875
    Prev
    Next
    INDEX
    Explanations

    say “n” sounds

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    狱
    -21.63
    粟
    -21.25
     prick
    -20.88
    indh
    -20.63
    immel
    -20.63
    ENCY
    -20.50
    FRING
    -19.50
    vince
    -19.50
    indx
    -19.13
     Flint
    -19.00
    POSITIVE LOGITS
    yon
    21.88
     Leone
    20.38
     Eaton
    19.13
    奥巴
    19.13
     Cameron
    18.13
     Hasan
    16.50
     Leon
    16.50
     Herman
    16.38
    ean
    15.88
    �
    15.81
    Activations Density 1.264%

    No Known Activations